github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[extractor] Make search_json able to parse lists

Browse source 
Now `contains_pattern` can be set to `\[.+\]`
This commit is contained in:
pukkandan 2022-10-03 16:50:27 +05:30
parent a83333c432
commit 8b7fb8b60d
No known key found for this signature in database
GPG key ID: 7EEE9E1E817D0A39
3 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
yt_dlp/extractor/common.py
View file

@ -1227,7 +1227,7 @@ def _search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, f
return None return None
def _search_json(self, start_pattern, string, name, video_id, *, end_pattern='', def _search_json(self, start_pattern, string, name, video_id, *, end_pattern='',
contains_pattern='(?s:.+)', fatal=True, default=NO_DEFAULT, **kwargs): contains_pattern=r'{(?s:.+)}', fatal=True, default=NO_DEFAULT, **kwargs):
"""Searches string for the JSON object specified by start_pattern""" """Searches string for the JSON object specified by start_pattern"""
# NB: end_pattern is only used to reduce the size of the initial match # NB: end_pattern is only used to reduce the size of the initial match
if default is NO_DEFAULT: if default is NO_DEFAULT:
@ -1236,7 +1236,7 @@ def _search_json(self, start_pattern, string, name, video_id, *, end_pattern='',
fatal, has_default = False, True fatal, has_default = False, True
json_string = self._search_regex( json_string = self._search_regex(
rf'(?:{start_pattern})\s*(?P<json>{{\s*(?:{contains_pattern})\s*}})\s*(?:{end_pattern})', rf'(?:{start_pattern})\s*(?P<json>{contains_pattern})\s*(?:{end_pattern})',
string, name, group='json', fatal=fatal, default=None if has_default else NO_DEFAULT) string, name, group='json', fatal=fatal, default=None if has_default else NO_DEFAULT)
if not json_string: if not json_string:
return default return default

2
yt_dlp/extractor/dropbox.py
View file

@ -54,7 +54,7 @@ def _real_extract(self, url):
raise ExtractorError('Password protected video, use --video-password <password>', expected=True) raise ExtractorError('Password protected video, use --video-password <password>', expected=True)
info_json = self._search_json(r'InitReact\.mountComponent\(.*?,', webpage, 'mountComponent', video_id, info_json = self._search_json(r'InitReact\.mountComponent\(.*?,', webpage, 'mountComponent', video_id,
contains_pattern=r'.+?"preview".+?', end_pattern=r'\)')['props'] contains_pattern=r'{.+?"preview".+?}', end_pattern=r'\)')['props']
transcode_url = traverse_obj(info_json, ((None, 'preview'), 'file', 'preview', 'content', 'transcode_url'), get_all=False) transcode_url = traverse_obj(info_json, ((None, 'preview'), 'file', 'preview', 'content', 'transcode_url'), get_all=False)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(transcode_url, video_id) formats, subtitles = self._extract_m3u8_formats_and_subtitles(transcode_url, video_id)

2
yt_dlp/extractor/radiofrance.py
View file

@ -84,7 +84,7 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
# _search_json_ld doesn't correctly handle this. See https://github.com/yt-dlp/yt-dlp/pull/3874#discussion_r891903846 # _search_json_ld doesn't correctly handle this. See https://github.com/yt-dlp/yt-dlp/pull/3874#discussion_r891903846
video_data = self._search_json('', webpage, 'audio data', display_id, contains_pattern=r'\s*"@type"\s*:\s*"AudioObject"\s*.+') video_data = self._search_json('', webpage, 'audio data', display_id, contains_pattern=r'{\s*"@type"\s*:\s*"AudioObject".+}')
return { return {
'id': video_id, 'id': video_id,